CN103473354A - Insurance recommendation system framework and insurance recommendation method based on e-commerce platform - Google Patents
Insurance recommendation system framework and insurance recommendation method based on e-commerce platform Download PDFInfo
- Publication number
- CN103473354A CN103473354A CN2013104430080A CN201310443008A CN103473354A CN 103473354 A CN103473354 A CN 103473354A CN 2013104430080 A CN2013104430080 A CN 2013104430080A CN 201310443008 A CN201310443008 A CN 201310443008A CN 103473354 A CN103473354 A CN 103473354A
- Authority
- CN
- China
- Prior art keywords
- recommendation
- user
- insurance
- feature
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the technical field of recommendation systems in the information technology and relates to an insurance recommendation system framework and an insurance recommendation method based on an e-commerce platform. The insurance recommendation system framework and the insurance recommendation method are particularly suitable for insurance recommendation application under the Internet environment and also have reference significance to the recommendation of other commodities based on the e-commerce. Aiming at the characteristic of being based on an insurance e-commerce platform, a generalized system framework for an individualized insurance recommendation system is disclosed; in consideration of the specific scene of the insurance e-commerce platform, an insurance individualized recommendation process based on the e-commerce platform is designed; all recommendation methods are integrated in one recommendation framework, the advantages of all recommendation methods are fully utilized and the goal of accurate and reliable individualized insurance recommendation is realized; two modes, i.e. an offline recommendation mode and an online recommendation mode are jointly used to guarantee the timeliness of the recommendation; recommendation results are explained and the behaviors of users on which each recommendation result is given are pointed out; due to the specificity of insurance recommendation, a reasonable recommendation result display interface is designed.
Description
Technical field
The invention belongs to the commending system technical field in infotech, be particularly suitable for the insurance based on ecommerce under the Internet environment and recommend, the commercial product recommending for other based on e-commerce platform all has reference.
Background technology
Along with high speed development and the widespread use of Internet technology, E-business applications are flourish.New business environment, when new business opportunity is provided for enterprise, has also proposed new challenge to enterprise.Customer relation management customer-centric is the key that in e-commerce environment, enterprise attracts and improve client's viscosity.How in fast changing electronic commerce times, to attract new client, and improve the user's experience of oneself, with the product or the service that enough attract clients, impel them to stay, become the main task of many e-commerce ventures.On the other hand, the client, in the face of so numerous selection, select own real requirement and also be equivalent to look for a needle in a haystack.The commending system of rising in recent years becomes one of important channel addressed these problems.
Commending system is exactly the next program to its recommendation information or commodity of hobby, custom according to individual subscriber.Initial research motivation comes from the information explosion that internet brings.Usually people find required content by means of search engine, but most of users are difficult to describe exactly with several brief key words the needs of oneself, consequently or can not get any result, or have to check one by one from a large amount of lists of returning.So imagination allows a program infer user's regard, what is observed is that the user likes, and what is that the user does not like, and then, automatically for the user filters out the content that the user likes, filters out the content that those users do not like.In the E-business applications field, recommended becomes the commercial affairs that businessman sells.At present, in the main flow e-commerce website, have many successful commending system application systems in the world, the object of recommendation comprises video disc, CD, books and other all kinds of commodity etc.
In recent years, insurance industry is combined day by day with e-commerce industry, becomes the frontier of insurance industry development.Traditional insurance sales all need to customize recommendation for client's demand by means of the marketing consultant, and this makes the ecommerce of insurance industry be different from the e-commerce platform of retail trade.This singularity requires the E-Insurance platform that powerful hommization commending system need to be provided, quick to facilitate the client, understands easily and choose the insurance of applicable self-demand.
Summary of the invention
For the characteristics based on the E-Insurance platform, the present invention proposes insurance recommendation system framework, flow process and implementation method based on ecommerce, there is following features:
1) designed the general architecture of personalized insurance commending system
2) consider the concrete scene of E-Insurance platform, designed the insurance personalized recommendation flow process based on e-commerce platform;
3) various recommend methods are integrated in to one and recommend, under framework, to take full advantage of the advantage of various recommend methods, realize accurately, personalized insurance recommends;
4) be combined with off-line and online two kinds of patterns, the promptness that assurance is recommended of recommending;
5) recommendation results is made an explanation, point out which behavior that each recommendation results is based on the user provides;
The singularity of 6) recommending for insurance, designed recommendation results and showed interface.
The accompanying drawing explanation
Fig. 1 system architecture of the present invention.
Fig. 2 the present invention does not have the client of information to enter the website schematic diagram.
Fig. 3 registered user of the present invention enters the website schematic diagram without browsing purchaser record.
The unregistered client of Fig. 4 the present invention (browsing record) enters the website schematic diagram.
Fig. 5 registered client of the present invention and browse purchaser record and enter the website schematic diagram.
Fig. 6 website homepage of the present invention is recommended schematic diagram.
Fig. 7 product classification page of the present invention is recommended schematic diagram.
Fig. 8 product details of the present invention page is recommended schematic diagram.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in further detail.
The corresponding Chinese implication of English proprietary word and abb.
| E-commerce(EC) | Ecommerce |
| Insurance | Insurance |
| Recommendation?system(RS) | Commending system |
| Recommendation?algorithm(RA) | Proposed algorithm |
| Architecture | System construction |
| Recommendation?workflow(RW) | Recommended flowsheet |
| On-line?recommendation | The online recommendation |
| Collaborative?filtering(CF) | Collaborative filtering |
| Content-based?recommendation | Content-based recommendation |
| Association-based?recommendation | Correlation recommendation |
| User-based?filtering | Filtration based on the user |
| Item-base?filtering | The filtration of product-based |
| Human?Interface(HI) | Man-machine interface |
One, system architecture
For E-Insurance website characteristic, designed the insurance recommendation system framework based on e-commerce platform as Fig. 1.Our emphasis user browses purchase data, and the self attributes characteristic of insurance products, be used to provide personalized commending system.System mainly is divided into three layers, and respectively: layer is implemented in recommending data/stratum of intellectual, recommended engine layer and recommendation.
Recommending data/stratum of intellectual is mainly customer data, insurance products data, purchase-transaction data and the client's behavioral data that the store electrons business web site provides; In addition, exactly from these extracting data, excavation for knowledge such as the various statistic supporting to recommend, rules, these knowledge store are in knowledge base.
The recommended engine layer comprises various data statisticss, mining algorithm and the concrete proposed algorithm of support recommending, and mainly contains: the statistical study of focus product, insurance products are sold association analysis, Collaborative Recommendation, content-based recommendation, the recommendation based on case etc.
Recommend to implement layer according to the online client access behavior from electronic business web station system, in conjunction with the relevant information in database and the relevant knowledge in knowledge base, utilize relevant data analysis and proposed algorithm, implement concrete the recommendation, and a webservice interface is provided, recommendation results is returned to the inline system of website.
Two, recommended flowsheet
Different scenes during for client access E-Insurance platform, designed concrete recommended flowsheet.Wherein, the customer information difference according to grasped is divided into the client: 1) brand-new client; 2) registration does not still almost have client's (having information not browse) of browsing histories; 3) client's (not having customer information) of browsing histories is arranged; 4) have and buy historical client.Corresponding to different situations, adopt different recommended flowsheets, as shown in Fig. 2,3,4,5.
Three, gordian technique
3.1 the user data of analyzing web site platform
Utilize the java program to do parsing to the user data of website, by resolving, can obtain user's behavioral data according to time sequence, behavior comprises: the page address of access, time, user's cookie information etc.System also can be filtered the interfere information of the reptile in daily record.Further, sum up user's frequency of the access to different product of every day.Use the oracle database to deposit the information of website user's information, product, user's purchase information (for e-commerce website) and marking information etc.
3.2 statistics is recommended
Statistics recommends to be intended to react better the general performance of each product under all user behaviors.Adopt following index to weigh the performance of product: number of clicks, purchase number of times, consumption sum, ejection number of times, clicking rate and buying rate etc.Wherein, ejection refers to: in one section session of user, and the product of last access.Be that the user has access to some products, do not continue at website visiting, be designated as ejection.In principle, wish to eject the extra high product of the frequency and do not appeared in recommendation list, so give negative value to this parameter.Because insurance products is one, ageing product is arranged, should give the better scoring of recent focus, process so do in time decline.Historical data and recent data recording are got off, and statistics, finally provide a marking respectively.
Suppose that the recent score value of above-mentioned each factor is x
1, x
2, x
3..., x
k, historical data is added up to such an extent that be divided into y
1, y
2, y
3..., y
k, give respectively them a
1, a
2, a
3..., a
kweight.Suppose that we have the decline factor t (0<t<1) of a time to historical data.So the comprehensive statistics mark of the product provided is:
The most at last according to score all products that sorts.A new user will preferentially see the mark the highest Products Show relevant with his the place page.
3.3 correlation rule is recommended
Correlation rule is recommended to have selected classical Apriori algorithm, and it is the classic algorithm in correlation rule field.This algorithm will find that the process of correlation rule is divided into two steps: the first step, by iteration, retrieves all frequent item sets in transaction database, and support is not less than the item collection of the threshold value of client's setting; Second step utilizes frequent item set to construct to meet the rule of client's the minimum confident degree.Specific practice is exactly: at first find out frequent 1-item collection, be designated as L1; Then utilize L1 to produce candidate C2, the item in C2 is judged and excavated L2, be i.e. frequent 2-item collection; Constantly so circulation is gone down until can't find more frequent k-item collection.Every excavation one deck Lk just needs the whole database of scanning one time.
3.4 collaborative filtering
Proposed a kind of collaborative filtering recommending method based on feature, its calculation procedure is as follows:
Step 1, according to the feature of article, original article-user is given a mark to matrix projection on different article characteristics, the feature-user who the obtains a plurality of polymerizations matrix of giving a mark.To each feature f
x, feature-user X matrix is made as M
x, in matrix, the value of the capable j of i row contains feature f for what user i marked
xjthe scoring average:
Step 2, for each user, add up the variance that it gives a mark on each feature, and portray the taste degree of user to this feature with this variance yields, variance is larger, shows that the user has deflection more by force to the value of this feature;
Step 3, based on each feature-user matrix of giving a mark, the marking value of predictive user to certain new article.Each feature-user's matrix, use collaborative filtering method all to obtain a prediction scoring, obtains like this one group of prediction scoring, P={p^1, and p^2 ... p^r}.
Step 4, utilize the variance of giving a mark on each feature of step 2, the marking predicted value that step 3 is calculated is weighted on average, obtains the final marking predicted value of user to these article.The weighted mean value that the prediction scoring of article is each signatures to predict scoring, establish SD (i, x) and mean that the prediction standards of grading of user i on feature x are poor, has:
Step 5, the marking predicted value based on final, carry out the article recommendation.
3.5 content-based recommendation
After the behavioural analysis for insurance purchasing group, find, the user buys a product, is also often because some important property of this product meet the demand of self, so from then on the recommendation of insurance products also can start with.After the business datum of having analyzed website, use the content of the attribute tags of insurance products as insurance products, carry out the similarity between counting yield with this, follow-up also can have the manual intervention similarity.Such great advantage is, a new product, as long as product attribute label accurately can be provided, it just can appear in its potential user's recommendation list very soon so.This is that general collaborative filtering can not provide.
About user content, can weigh according to user's occupation, age, sex and income etc. user's potential buying habit.Because often the approaching user of background buy the behavior of insurance products also can be comparatively approaching.Recommendation based on user content, can make up a new user in the historical viewings of not knowing him and purchase situation, by guiding it, inserts personal information, infers his potential demand.
Particularly, selected following attribute:
1) product macrotaxonomy (for example: traffic accident insurance, comprehensive casualty insurance, home journey insurance, travel insurance overseas);
2) insurance use zone (for example: China's Mainland, overseas, Southeast Asia, South Asia, Hongkong and Macro, Taiwan, Africa, the Middle East, Shen root country, Japan, Korea S);
3) characteristic ensures content (for example: medical treatment compensation, the double compensation of traffic, plateau specified disease, emergency relief, excessive risk motion, self-driving trip, property loss, airliner delay, loss of hire etc.);
4) accept insurance the age (for example: 0-3 one full year of life, 4-17 one full year of life, 18-65 one full year of life, more than 65 one full year of life);
5) ensure the time limit (for example: 7 days with interior, 1 month with interior, 1-3 month, within 3 months-1 year, 1 year, repeatedly come and go, annual resident).
Choose above attribute at the initial stage of system emphasis, the weight between attribute is can flexible.In addition, can choose the potential Insurance Attribute of valuing of user by for a long time to user's investigation and analysis, the weight of regulating these existing attributes, and increase when being necessary new attribute.These attributes are all self the product classification tag attributes from website.By the feedback of recommendation results, also can help website to improve self existing attribute system.After these attributes have been arranged, next step is exactly that product is calculated to similarity, just with the marking matrix that is similar to collaborative filtering, sets up the attributes similarity matrix of product.Here use Pearson similarity formula, after calculating similarity result, can in database, store this result, and recommend result similarly according to user's purchaser record, and as final product-based commending contents result.
3.6 recommend on line
After having introduced the algorithm that we choose, we can find, not only they have comparatively reasonably recommendation results for four kinds of algorithms that we choose, and they also have complementary effect to a certain extent.Collaborative filtering has versatility and recommendation results preferably to a great extent, but very large deficiency is arranged in cold start-up.Content-based recommendation, can partly solve cold start-up, and user or product are not new entirely, so recommendation results preferably can be arranged.Correlation rule, have the recommendation effect of dispersing very much universality, new user, arrives, and also do not know that, under his background attribute, we still can make personalized recommendation.Statistic algorithm has made up other algorithms in situation separately all not to be also had under suitable recommendation results, and we still can guide the user to buy some products salable.
So in sum, we give the content-based weight identical with collaborative filtering, in the situation that these 2 algorithms have recommendation results, we preferentially choose the recommendation results of these 2 kinds of algorithms.If these two kinds of arithmetic result deficiencies, do and supply with correlation rule and statistic algorithm successively.In addition, in order to embody preferably the purchase intention of user's current sessions, we also can be dynamically in conjunction with the user current browsing pages type, choose our recommendation results.Concrete minute following three kinds of situations:
1) homepage.For the user, in homepage, we can consider emphatically user's access source.Because website is also in period of expansion, website is certain to throw in advertisement in more relevant place so.We can originate to analyze according to user advertising his potential purchasing demand.For example the user comes from a health knowledge website, and we can preferentially choose the insurance products of healthy class in recommendation results so, if the user from tour site, we will certainly heighten the weight of travel accident insurance so.
2) product classification page.Classification page at product, illustrate that the user has had clear and definite demand to the own large series products that will buy, even some detail attribute also there is the requirement of oneself, so we can choose the insurance products of applicable current page as preferential recommendation in recommendation results, for diversity and the diversity that guarantees recommendation results, we also can avoid repeating with user's Search Results product.
3) product details page.At commodity details page, the user may browse or have and oneself want the product of buying, and at this moment, we infer that according to correlation rule the user may think further to continue the product of buying, and promote user's access efficiency.
In user's behavior quantity accumulation, after the growth of number of users, we can reduce the cycle of processed offline, and wherein the calculating of a part becomes the real-time calculating on line, makes like this our recommendation meet more accurately the recent demand of user.
4, operation interface
For the recommendation on line, aims of systems is according to different page scenes, and different recommendations is provided.A unified target is the current demand that meets as much as possible the user, improves access time and the buying rate of user in website.Following three types is specifically arranged:
1) website homepage: i.e. the homepage of website, the user starts to browse web sites from this page usually;
2) product classification page: the insurance products that the user enters concrete a certain classification by the click classifications label continues to browse;
3) product details page: specifically navigate to a insurance plan, the user can be bought product at this page.
For this three classes page, provide respectively the interface of the recommendation as shown in Fig. 6,7,8.
Above embodiment just is described for partial function of the present invention, but embodiment and accompanying drawing are not of the present invention for limiting.Without departing from the spirit and scope of the invention, any equivalence of doing changes or retouching, belongs to equally the present invention's protection domain.Therefore should to take the application's the content that claim was defined be standard to protection scope of the present invention.
Claims (9)
1. the insurance recommendation system framework based on e-commerce platform, it is divided into three layers, and respectively: recommending data/stratum of intellectual, recommended engine layer and recommend to implement layer is characterized in that:
Described recommending data/stratum of intellectual is customer data, insurance products data, purchase-transaction data and the client's behavioral data that the store electrons business web site provides; In addition, from these extracting data, excavation for the various statistic of supporting to recommend, the knowledge of rule, these knowledge store are in knowledge base;
Described recommended engine layer comprises various data statisticss, mining algorithm and the concrete proposed algorithm of support recommending, and includes: the statistical study of focus product, insurance products are sold association analysis, Collaborative Recommendation, content-based recommendation, the recommendation based on case;
Described recommendation is implemented layer according to the online client access behavior from electronic business web station system, in conjunction with the relevant information in database and the relevant knowledge in knowledge base, utilize relevant data analysis and proposed algorithm, implement concrete the recommendation, and a webservice interface is provided, recommendation results is returned to the inline system of website.
2. the insurance recommend method based on e-commerce platform, be applicable to insurance recommendation system framework claimed in claim 1, be based on the insurance exemplary application of e-commerce platform under the Internet environment, it is integrated in one by multiple recommend method and recommends under framework, gives personalized insurance for different users and recommends; The collaborative filtering of use based on feature, increase this factor of user preference, and user's marking is decayed in time, and user behavior data more remote is endowed lower weight, and up-to-date user is endowed lower weights; Recommendation results is made an explanation, point out which behavior that each recommendation results is based on the user provides; The singularity of recommending for insurance, designed recommendation results and showed interface.
3. insurance recommend method according to claim 2 is characterized in that: by the behavioral data of resolving the user, the user is divided, described behavioral data comprises: the page address of access, time, user's cookie information.
4. insurance recommend method according to claim 2, it is characterized in that: described different user is divided into: brand-new user; Log-on message is arranged but there is no the user of browsing histories; Browsing histories is arranged but there is no the user of log-on message; Have and buy historical user.
5. insurance recommend method according to claim 2, is characterized in that, described personalized insurance is recommended to comprise: statistics recommendation, correlation rule recommendation, collaborative filtering recommending, content-based recommendation.
6. insurance recommend method according to claim 5, is characterized in that, described statistics is recommended, and adopts following index to weigh the performance of product: number of clicks, purchase number of times, consumption sum, ejection number of times, clicking rate and buying rate; Wherein, ejection refers to: the product of last access in one section session of user, and the user has access to some products, does not continue at this website visiting, is designated as ejection; Eject the extra high product of the frequency and do not appeared in recommendation list, to this parameter, give negative value; Insurance products is done the decline processing in time simultaneously; Historical data and recent data recording are got off, and statistics, finally provide a marking respectively;
The recent score value of above-mentioned each factor is x
1, x
2, x
3..., x
k, historical data is added up to such an extent that be divided into y
1, y
2, y
3..., y
k, give respectively them a
1, a
2, a
3..., a
kweight; Historical data has the decline factor t (0<t<1) of a time; The comprehensive statistics mark of a product is:
According to score all products that sorts.
7. insurance recommend method according to claim 5, it is characterized in that, described correlation rule is recommended to select the Apriori algorithm will find that the process of correlation rule is divided into two steps: the first step is passed through iteration, retrieve all frequent item sets in transaction database, support is not less than the item collection of the threshold value of client's setting; Second step utilizes frequent item set to construct to meet the rule of client's the minimum confident degree; Specific practice is exactly: at first find out frequent 1-item collection, be designated as L1; Then utilize L1 to produce candidate C2, the item in C2 is judged and excavated L2, be i.e. frequent 2-item collection; Constantly so circulation is gone down until can't find more frequent k-item collection; Every excavation one deck Lk just needs the whole database of scanning one time.
8. insurance recommend method according to claim 5, is characterized in that, described collaborative filtering recommending is a kind of recommend method based on feature, and its calculation procedure is as follows:
Step 1, according to the feature of article, original article-user is given a mark to matrix projection on different article characteristics, the feature-user who the obtains a plurality of polymerizations matrix of giving a mark; To each feature f
x, feature-user X matrix is made as M
x, in matrix, the value of the capable j of i row contains feature f for what user i marked
xjthe scoring average:
Step 2, for each user, add up the variance that it gives a mark on each feature, and portray the taste degree of user to this feature with this variance yields, variance is larger, shows that the user has deflection more by force to the value of this feature;
Step 3, based on each feature-user matrix of giving a mark, the marking value of predictive user to certain new article; Each feature-user's matrix, use collaborative filtering method all to obtain a prediction scoring, obtains like this one group of prediction scoring, P={p^1, and p^2 ... p^r};
Step 4, utilize the variance of giving a mark on each feature of step 2, the marking predicted value that step 3 is calculated is weighted on average, obtains the final marking predicted value of user to these article; The weighted mean value that the prediction scoring of article is each signatures to predict scoring, establish SD (i, x) and mean that the prediction standards of grading of user i on feature x are poor, has:
Step 5, the marking predicted value based on final, carry out the article recommendation.
9. insurance recommend method according to claim 5, is characterized in that, described content-based be recommended in the business datum of having analyzed website after, use the content of the attribute tags of insurance products as insurance products, carry out the similarity between counting yield with this;
About user content, weigh user's potential buying habit according to user's occupation, age, sex and income;
The attribute of described insurance products comprises: product classification, insurance are used zone, characteristic to ensure content, the age of accepting insurance, are ensured the time limit; Weight between attribute is to regulate;
Use Pearson similarity formula, set up the attributes similarity matrix of product, after calculating similarity result, this result of storage in database, and recommend result similarly according to user's purchaser record, and as final product-based commending contents result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013104430080A CN103473354A (en) | 2013-09-25 | 2013-09-25 | Insurance recommendation system framework and insurance recommendation method based on e-commerce platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013104430080A CN103473354A (en) | 2013-09-25 | 2013-09-25 | Insurance recommendation system framework and insurance recommendation method based on e-commerce platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103473354A true CN103473354A (en) | 2013-12-25 |
Family
ID=49798202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013104430080A Pending CN103473354A (en) | 2013-09-25 | 2013-09-25 | Insurance recommendation system framework and insurance recommendation method based on e-commerce platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103473354A (en) |
Cited By (63)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104616179A (en) * | 2015-03-06 | 2015-05-13 | 焦点科技股份有限公司 | Insurance product sorting method applicable to insurance e-commerce platform |
| CN104463630B (en) * | 2014-12-11 | 2015-08-26 | 新一站保险代理有限公司 | A kind of Products Show method and system based on net purchase insurance products characteristic |
| CN105096149A (en) * | 2014-05-09 | 2015-11-25 | 华为软件技术有限公司 | Service content product correlation analysis method and apparatus |
| WO2015196397A1 (en) * | 2014-06-25 | 2015-12-30 | 北京百付宝科技有限公司 | Method and device for data mining based on user's search behaviour |
| CN105260922A (en) * | 2015-10-15 | 2016-01-20 | 广东欧珀移动通信有限公司 | Commodity information matching method and commodity information matching device |
| CN105740468A (en) * | 2016-03-07 | 2016-07-06 | 达而观信息科技（上海）有限公司 | Individuation recommendation method and system combined with content publisher information |
| CN106530010A (en) * | 2016-11-15 | 2017-03-22 | 平安科技（深圳）有限公司 | Collaborative filtering method and apparatus based on fusion of time factor |
| CN103810030B (en) * | 2014-02-20 | 2017-04-05 | 北京奇虎科技有限公司 | It is a kind of based on the application recommendation method of mobile terminal application market, apparatus and system |
| CN106598985A (en) * | 2015-10-16 | 2017-04-26 | 阿里巴巴集团控股有限公司 | Information recommendation method and device |
| CN106709767A (en) * | 2017-03-07 | 2017-05-24 | 携程计算机技术（上海）有限公司 | Personalized recommendation method and system of OTA (online travel website) hotels |
| CN106780052A (en) * | 2017-01-10 | 2017-05-31 | 上海诺悦智能科技有限公司 | Method and system are recommended in insurance service based on classification customer behavior analysis |
| CN107146161A (en) * | 2017-04-05 | 2017-09-08 | 昆明理工大学 | A kind of insurance search method selected based on classification |
| CN107247726A (en) * | 2017-04-28 | 2017-10-13 | 北京神州泰岳软件股份有限公司 | Suitable for the implementation method and device of the intelligent robot of multi-service scene |
| CN107330719A (en) * | 2017-06-09 | 2017-11-07 | 上海新概念保险经纪有限公司 | A kind of insurance products recommend method and system |
| CN107689005A (en) * | 2017-03-14 | 2018-02-13 | 平安科技（深圳）有限公司 | A kind of methods of exhibiting and device for insuring track |
| CN107729443A (en) * | 2017-09-29 | 2018-02-23 | 平安科技（深圳）有限公司 | Loan product promotion method, device and computer-readable recording medium |
| CN107767276A (en) * | 2016-08-23 | 2018-03-06 | 平安科技（深圳）有限公司 | Product information auto recommending method and system |
| CN107798034A (en) * | 2017-04-10 | 2018-03-13 | 平安科技（深圳）有限公司 | A kind of generation method of service page and the generating means of service page |
| CN108009885A (en) * | 2017-11-30 | 2018-05-08 | 广州云移信息科技有限公司 | Commodity information recommendation method and system |
| CN108154396A (en) * | 2017-12-26 | 2018-06-12 | 成都生命基线科技有限公司 | A kind of reagent consumptive material intelligently pushing method in biology research experiments platform |
| CN108230162A (en) * | 2017-12-29 | 2018-06-29 | 泰康保险集团股份有限公司 | Method, apparatus, storage medium and the electronic equipment that insurance service is recommended |
| CN108429865A (en) * | 2017-02-13 | 2018-08-21 | 中国移动通信集团广东有限公司 | A kind of Products Show processing method and processing device |
| CN108596705A (en) * | 2018-03-23 | 2018-09-28 | 郑州大学西亚斯国际学院 | A kind of commodity suitable for e-commerce recommend method and system with information classification |
| CN108614859A (en) * | 2018-03-26 | 2018-10-02 | 平安科技（深圳）有限公司 | Intelligent search method, server and storage medium |
| CN108803970A (en) * | 2018-05-08 | 2018-11-13 | 平安科技（深圳）有限公司 | Scene matching methods of exhibiting and terminal device |
| CN109191186A (en) * | 2018-08-16 | 2019-01-11 | 安徽超清科技股份有限公司 | A kind of intelligent recommendation system based on big data |
| CN109300054A (en) * | 2018-11-27 | 2019-02-01 | 泰康保险集团股份有限公司 | Insurance products recommended method, device, server and storage medium |
| CN109300045A (en) * | 2018-10-25 | 2019-02-01 | 平安科技（深圳）有限公司 | Financial product recommended method, device, computer equipment and storage medium |
| CN109300017A (en) * | 2018-10-27 | 2019-02-01 | 平安科技（深圳）有限公司 | Declaration form recommended method, device, server and storage medium based on data analysis |
| CN109377384A (en) * | 2018-09-03 | 2019-02-22 | 阿里巴巴集团控股有限公司 | The determination method, apparatus and server of health insurance |
| WO2019052257A1 (en) * | 2017-09-15 | 2019-03-21 | Beijing Didi Infinity Technology And Development Co., Ltd. | Artificial intelligent systems and methods for recommending at least one insurance company |
| CN109559130A (en) * | 2018-10-26 | 2019-04-02 | 阿里巴巴集团控股有限公司 | A kind of processing method of insurance business, device and equipment |
| CN109858948A (en) * | 2018-12-25 | 2019-06-07 | 国网北京市电力公司 | The determination method and apparatus of power customer marketing strategy |
| CN109949165A (en) * | 2018-11-28 | 2019-06-28 | 阿里巴巴集团控股有限公司 | Information verification method and device |
| USD854552S1 (en) | 2018-04-16 | 2019-07-23 | Allstate Insurance Company | Display screen with animated graphical user interface |
| USD855061S1 (en) | 2018-04-16 | 2019-07-30 | Allstate Insurance Company | Display screen with graphical user interface |
| USD855060S1 (en) | 2018-04-16 | 2019-07-30 | Allstate Insurance Company | Display screen with graphical user interface |
| USD855062S1 (en) | 2018-04-16 | 2019-07-30 | Allstate Insurance Company | Display screen with graphical user interface |
| US10387513B2 (en) | 2015-08-28 | 2019-08-20 | Yandex Europe Ag | Method and apparatus for generating a recommended content list |
| US10387115B2 (en) * | 2015-09-28 | 2019-08-20 | Yandex Europe Ag | Method and apparatus for generating a recommended set of items |
| US10394420B2 (en) | 2016-05-12 | 2019-08-27 | Yandex Europe Ag | Computer-implemented method of generating a content recommendation interface |
| US10430481B2 (en) | 2016-07-07 | 2019-10-01 | Yandex Europe Ag | Method and apparatus for generating a content recommendation in a recommendation system |
| WO2019184281A1 (en) * | 2018-03-26 | 2019-10-03 | 平安科技（深圳）有限公司 | Method and server for dynamically managing product services, and storage medium |
| US10452731B2 (en) | 2015-09-28 | 2019-10-22 | Yandex Europe Ag | Method and apparatus for generating a recommended set of items for a user |
| CN110443664A (en) * | 2018-05-04 | 2019-11-12 | 阿里巴巴集团控股有限公司 | Information transmission system, optical projection system, method, apparatus and electronic equipment |
| USD882600S1 (en) | 2017-01-13 | 2020-04-28 | Yandex Europe Ag | Display screen with graphical user interface |
| US10674215B2 (en) | 2018-09-14 | 2020-06-02 | Yandex Europe Ag | Method and system for determining a relevancy parameter for content item |
| US10706325B2 (en) | 2016-07-07 | 2020-07-07 | Yandex Europe Ag | Method and apparatus for selecting a network resource as a source of content for a recommendation system |
| CN111814032A (en) * | 2019-04-11 | 2020-10-23 | 阿里巴巴集团控股有限公司 | Cold start recommendation method and device and electronic equipment |
| CN111967934A (en) * | 2020-08-12 | 2020-11-20 | 上海辰山植物园 | Intelligent recommendation method for green plant application in online shopping mall |
| CN112182416A (en) * | 2020-09-10 | 2021-01-05 | 北京市科学技术情报研究所 | Scientific and technological resource dynamic collaborative filtering recommendation method based on user group preference |
| CN112906998A (en) * | 2019-11-19 | 2021-06-04 | 泰康保险集团股份有限公司 | Data processing system and method for reassigning clerks to customers of an insurance company |
| CN112966098A (en) * | 2021-03-15 | 2021-06-15 | 中国美术学院 | Product and matching supply relation visualization method and system thereof |
| US11086888B2 (en) | 2018-10-09 | 2021-08-10 | Yandex Europe Ag | Method and system for generating digital content recommendation |
| US11199943B2 (en) | 2018-04-06 | 2021-12-14 | Allstate Insurance Company | Processing system having a machine learning engine for providing a selectable item availability output |
| US11263217B2 (en) | 2018-09-14 | 2022-03-01 | Yandex Europe Ag | Method of and system for determining user-specific proportions of content for recommendation |
| US11276079B2 (en) | 2019-09-09 | 2022-03-15 | Yandex Europe Ag | Method and system for meeting service level of content item promotion |
| US11276076B2 (en) | 2018-09-14 | 2022-03-15 | Yandex Europe Ag | Method and system for generating a digital content recommendation |
| US11288333B2 (en) | 2018-10-08 | 2022-03-29 | Yandex Europe Ag | Method and system for estimating user-item interaction data based on stored interaction data by using multiple models |
| CN115829293A (en) * | 2023-01-05 | 2023-03-21 | 优保联(北京)科技有限公司 | Insurance scheme matching method, insurance scheme matching system and related devices |
| US11635877B2 (en) | 2018-04-06 | 2023-04-25 | Allstate Insurance Company | Processing system having a machine learning engine for providing a selectable item availability output |
| CN117892011A (en) * | 2024-03-14 | 2024-04-16 | 众星北斗(北京)科技发展有限公司 | Intelligent information pushing method and system based on big data |
| CN117974331A (en) * | 2024-03-28 | 2024-05-03 | 探保网络科技(广州)有限公司 | Insurance recommendation method and system based on electronic commerce platform |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020138308A1 (en) * | 2001-03-22 | 2002-09-26 | Fujitsu Limited | Insurance task processing method, insurance task processing program, computer-readable storage medium recorded with insurance task processing program, and insurance task processing system |
| CN102663626A (en) * | 2012-04-26 | 2012-09-12 | 焦点科技股份有限公司 | Collaborative filtering recommended method based on provincial characteristics |
-
2013
- 2013-09-25 CN CN2013104430080A patent/CN103473354A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020138308A1 (en) * | 2001-03-22 | 2002-09-26 | Fujitsu Limited | Insurance task processing method, insurance task processing program, computer-readable storage medium recorded with insurance task processing program, and insurance task processing system |
| CN102663626A (en) * | 2012-04-26 | 2012-09-12 | 焦点科技股份有限公司 | Collaborative filtering recommended method based on provincial characteristics |
Non-Patent Citations (1)
| Title |
|---|
| 周洋: "个性化推荐系统推荐引擎原型系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 2, 15 August 2007 (2007-08-15), pages 9 - 37 * |
Cited By (87)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103810030B (en) * | 2014-02-20 | 2017-04-05 | 北京奇虎科技有限公司 | It is a kind of based on the application recommendation method of mobile terminal application market, apparatus and system |
| CN105096149A (en) * | 2014-05-09 | 2015-11-25 | 华为软件技术有限公司 | Service content product correlation analysis method and apparatus |
| CN105096149B (en) * | 2014-05-09 | 2019-02-01 | 华为软件技术有限公司 | Business tine method for analyzing product association and device |
| US10896461B2 (en) | 2014-06-25 | 2021-01-19 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for data mining based on users' search behavior |
| WO2015196397A1 (en) * | 2014-06-25 | 2015-12-30 | 北京百付宝科技有限公司 | Method and device for data mining based on user's search behaviour |
| CN105556514A (en) * | 2014-06-25 | 2016-05-04 | 北京百付宝科技有限公司 | Method and device for data mining based on user's search behaviour |
| CN104463630B (en) * | 2014-12-11 | 2015-08-26 | 新一站保险代理有限公司 | A kind of Products Show method and system based on net purchase insurance products characteristic |
| CN104616179A (en) * | 2015-03-06 | 2015-05-13 | 焦点科技股份有限公司 | Insurance product sorting method applicable to insurance e-commerce platform |
| US10387513B2 (en) | 2015-08-28 | 2019-08-20 | Yandex Europe Ag | Method and apparatus for generating a recommended content list |
| US10387115B2 (en) * | 2015-09-28 | 2019-08-20 | Yandex Europe Ag | Method and apparatus for generating a recommended set of items |
| US10452731B2 (en) | 2015-09-28 | 2019-10-22 | Yandex Europe Ag | Method and apparatus for generating a recommended set of items for a user |
| CN105260922A (en) * | 2015-10-15 | 2016-01-20 | 广东欧珀移动通信有限公司 | Commodity information matching method and commodity information matching device |
| CN106598985A (en) * | 2015-10-16 | 2017-04-26 | 阿里巴巴集团控股有限公司 | Information recommendation method and device |
| CN106598985B (en) * | 2015-10-16 | 2020-03-27 | 阿里巴巴集团控股有限公司 | Information recommendation method and device |
| CN105740468A (en) * | 2016-03-07 | 2016-07-06 | 达而观信息科技（上海）有限公司 | Individuation recommendation method and system combined with content publisher information |
| CN105740468B (en) * | 2016-03-07 | 2019-10-18 | 达而观信息科技（上海）有限公司 | A kind of personalized recommendation method and system of combined content issuer information |
| US10394420B2 (en) | 2016-05-12 | 2019-08-27 | Yandex Europe Ag | Computer-implemented method of generating a content recommendation interface |
| US10706325B2 (en) | 2016-07-07 | 2020-07-07 | Yandex Europe Ag | Method and apparatus for selecting a network resource as a source of content for a recommendation system |
| US10430481B2 (en) | 2016-07-07 | 2019-10-01 | Yandex Europe Ag | Method and apparatus for generating a content recommendation in a recommendation system |
| CN107767276A (en) * | 2016-08-23 | 2018-03-06 | 平安科技（深圳）有限公司 | Product information auto recommending method and system |
| CN106530010A (en) * | 2016-11-15 | 2017-03-22 | 平安科技（深圳）有限公司 | Collaborative filtering method and apparatus based on fusion of time factor |
| CN106530010B (en) * | 2016-11-15 | 2017-12-12 | 平安科技（深圳）有限公司 | The collaborative filtering method and device of time of fusion factor |
| US10565525B2 (en) | 2016-11-15 | 2020-02-18 | Ping An Technology (Shenzhen) Co., Ltd. | Collaborative filtering method, apparatus, server and storage medium in combination with time factor |
| JP2019507398A (en) * | 2016-11-15 | 2019-03-14 | 平安科技（深▲せん▼）有限公司 | Collaborative filtering method, apparatus, server, and storage medium for fusing time factors |
| CN106780052A (en) * | 2017-01-10 | 2017-05-31 | 上海诺悦智能科技有限公司 | Method and system are recommended in insurance service based on classification customer behavior analysis |
| USD892846S1 (en) | 2017-01-13 | 2020-08-11 | Yandex Europe Ag | Display screen with graphical user interface |
| USD892847S1 (en) | 2017-01-13 | 2020-08-11 | Yandex Europe Ag | Display screen with graphical user interface |
| USD882600S1 (en) | 2017-01-13 | 2020-04-28 | Yandex Europe Ag | Display screen with graphical user interface |
| USD980246S1 (en) | 2017-01-13 | 2023-03-07 | Yandex Europe Ag | Display screen with graphical user interface |
| USD890802S1 (en) | 2017-01-13 | 2020-07-21 | Yandex Europe Ag | Display screen with graphical user interface |
| CN108429865B (en) * | 2017-02-13 | 2020-10-16 | 中国移动通信集团广东有限公司 | Product recommendation processing method and device |
| CN108429865A (en) * | 2017-02-13 | 2018-08-21 | 中国移动通信集团广东有限公司 | A kind of Products Show processing method and processing device |
| CN106709767A (en) * | 2017-03-07 | 2017-05-24 | 携程计算机技术（上海）有限公司 | Personalized recommendation method and system of OTA (online travel website) hotels |
| CN107689005B (en) * | 2017-03-14 | 2020-12-25 | 平安科技（深圳）有限公司 | Insurance track display method and device |
| WO2018166302A1 (en) * | 2017-03-14 | 2018-09-20 | 平安科技（深圳）有限公司 | Display method and device for insurance trajectory |
| CN107689005A (en) * | 2017-03-14 | 2018-02-13 | 平安科技（深圳）有限公司 | A kind of methods of exhibiting and device for insuring track |
| CN107146161A (en) * | 2017-04-05 | 2017-09-08 | 昆明理工大学 | A kind of insurance search method selected based on classification |
| CN107798034A (en) * | 2017-04-10 | 2018-03-13 | 平安科技（深圳）有限公司 | A kind of generation method of service page and the generating means of service page |
| CN107247726A (en) * | 2017-04-28 | 2017-10-13 | 北京神州泰岳软件股份有限公司 | Suitable for the implementation method and device of the intelligent robot of multi-service scene |
| CN107247726B (en) * | 2017-04-28 | 2018-06-08 | 北京神州泰岳软件股份有限公司 | Suitable for the implementation method and device of the intelligent robot of multi-service scene |
| CN107330719A (en) * | 2017-06-09 | 2017-11-07 | 上海新概念保险经纪有限公司 | A kind of insurance products recommend method and system |
| WO2019052257A1 (en) * | 2017-09-15 | 2019-03-21 | Beijing Didi Infinity Technology And Development Co., Ltd. | Artificial intelligent systems and methods for recommending at least one insurance company |
| CN107729443A (en) * | 2017-09-29 | 2018-02-23 | 平安科技（深圳）有限公司 | Loan product promotion method, device and computer-readable recording medium |
| CN108009885A (en) * | 2017-11-30 | 2018-05-08 | 广州云移信息科技有限公司 | Commodity information recommendation method and system |
| CN108154396A (en) * | 2017-12-26 | 2018-06-12 | 成都生命基线科技有限公司 | A kind of reagent consumptive material intelligently pushing method in biology research experiments platform |
| CN108230162B (en) * | 2017-12-29 | 2022-01-11 | 泰康保险集团股份有限公司 | Insurance service recommendation method and device, storage medium and electronic equipment |
| CN108230162A (en) * | 2017-12-29 | 2018-06-29 | 泰康保险集团股份有限公司 | Method, apparatus, storage medium and the electronic equipment that insurance service is recommended |
| CN108596705A (en) * | 2018-03-23 | 2018-09-28 | 郑州大学西亚斯国际学院 | A kind of commodity suitable for e-commerce recommend method and system with information classification |
| WO2019184281A1 (en) * | 2018-03-26 | 2019-10-03 | 平安科技（深圳）有限公司 | Method and server for dynamically managing product services, and storage medium |
| CN108614859A (en) * | 2018-03-26 | 2018-10-02 | 平安科技（深圳）有限公司 | Intelligent search method, server and storage medium |
| US11635877B2 (en) | 2018-04-06 | 2023-04-25 | Allstate Insurance Company | Processing system having a machine learning engine for providing a selectable item availability output |
| US11199943B2 (en) | 2018-04-06 | 2021-12-14 | Allstate Insurance Company | Processing system having a machine learning engine for providing a selectable item availability output |
| USD855060S1 (en) | 2018-04-16 | 2019-07-30 | Allstate Insurance Company | Display screen with graphical user interface |
| USD855062S1 (en) | 2018-04-16 | 2019-07-30 | Allstate Insurance Company | Display screen with graphical user interface |
| USD855061S1 (en) | 2018-04-16 | 2019-07-30 | Allstate Insurance Company | Display screen with graphical user interface |
| USD854552S1 (en) | 2018-04-16 | 2019-07-23 | Allstate Insurance Company | Display screen with animated graphical user interface |
| CN110443664A (en) * | 2018-05-04 | 2019-11-12 | 阿里巴巴集团控股有限公司 | Information transmission system, optical projection system, method, apparatus and electronic equipment |
| CN108803970A (en) * | 2018-05-08 | 2018-11-13 | 平安科技（深圳）有限公司 | Scene matching methods of exhibiting and terminal device |
| CN108803970B (en) * | 2018-05-08 | 2021-06-04 | 平安科技（深圳）有限公司 | Scene matching display method and terminal equipment |
| CN109191186A (en) * | 2018-08-16 | 2019-01-11 | 安徽超清科技股份有限公司 | A kind of intelligent recommendation system based on big data |
| CN109377384A (en) * | 2018-09-03 | 2019-02-22 | 阿里巴巴集团控股有限公司 | The determination method, apparatus and server of health insurance |
| US11276076B2 (en) | 2018-09-14 | 2022-03-15 | Yandex Europe Ag | Method and system for generating a digital content recommendation |
| US11263217B2 (en) | 2018-09-14 | 2022-03-01 | Yandex Europe Ag | Method of and system for determining user-specific proportions of content for recommendation |
| US10674215B2 (en) | 2018-09-14 | 2020-06-02 | Yandex Europe Ag | Method and system for determining a relevancy parameter for content item |
| US11288333B2 (en) | 2018-10-08 | 2022-03-29 | Yandex Europe Ag | Method and system for estimating user-item interaction data based on stored interaction data by using multiple models |
| US11086888B2 (en) | 2018-10-09 | 2021-08-10 | Yandex Europe Ag | Method and system for generating digital content recommendation |
| CN109300045A (en) * | 2018-10-25 | 2019-02-01 | 平安科技（深圳）有限公司 | Financial product recommended method, device, computer equipment and storage medium |
| CN109559130A (en) * | 2018-10-26 | 2019-04-02 | 阿里巴巴集团控股有限公司 | A kind of processing method of insurance business, device and equipment |
| CN109300017A (en) * | 2018-10-27 | 2019-02-01 | 平安科技（深圳）有限公司 | Declaration form recommended method, device, server and storage medium based on data analysis |
| CN109300054A (en) * | 2018-11-27 | 2019-02-01 | 泰康保险集团股份有限公司 | Insurance products recommended method, device, server and storage medium |
| CN109949165A (en) * | 2018-11-28 | 2019-06-28 | 阿里巴巴集团控股有限公司 | Information verification method and device |
| CN109949165B (en) * | 2018-11-28 | 2020-07-24 | 阿里巴巴集团控股有限公司 | Information checking method and device |
| CN109858948A (en) * | 2018-12-25 | 2019-06-07 | 国网北京市电力公司 | The determination method and apparatus of power customer marketing strategy |
| CN111814032B (en) * | 2019-04-11 | 2024-05-28 | 阿里巴巴集团控股有限公司 | Cold start recommendation method and device and electronic equipment |
| CN111814032A (en) * | 2019-04-11 | 2020-10-23 | 阿里巴巴集团控股有限公司 | Cold start recommendation method and device and electronic equipment |
| US11276079B2 (en) | 2019-09-09 | 2022-03-15 | Yandex Europe Ag | Method and system for meeting service level of content item promotion |
| CN112906998A (en) * | 2019-11-19 | 2021-06-04 | 泰康保险集团股份有限公司 | Data processing system and method for reassigning clerks to customers of an insurance company |
| CN111967934B (en) * | 2020-08-12 | 2022-11-18 | 上海辰山植物园 | Intelligent recommendation method for green plant application in online shopping mall |
| CN111967934A (en) * | 2020-08-12 | 2020-11-20 | 上海辰山植物园 | Intelligent recommendation method for green plant application in online shopping mall |
| CN112182416A (en) * | 2020-09-10 | 2021-01-05 | 北京市科学技术情报研究所 | Scientific and technological resource dynamic collaborative filtering recommendation method based on user group preference |
| CN112182416B (en) * | 2020-09-10 | 2024-02-02 | 北京市科学技术情报研究所 | Scientific and technological resource dynamic collaborative filtering recommendation method based on user group preference |
| CN112966098A (en) * | 2021-03-15 | 2021-06-15 | 中国美术学院 | Product and matching supply relation visualization method and system thereof |
| CN115829293A (en) * | 2023-01-05 | 2023-03-21 | 优保联(北京)科技有限公司 | Insurance scheme matching method, insurance scheme matching system and related devices |
| CN117892011A (en) * | 2024-03-14 | 2024-04-16 | 众星北斗(北京)科技发展有限公司 | Intelligent information pushing method and system based on big data |
| CN117892011B (en) * | 2024-03-14 | 2024-05-17 | 众星北斗(北京)科技发展有限公司 | Intelligent information pushing method and system based on big data |
| CN117974331A (en) * | 2024-03-28 | 2024-05-03 | 探保网络科技(广州)有限公司 | Insurance recommendation method and system based on electronic commerce platform |
| CN117974331B (en) * | 2024-03-28 | 2024-06-11 | 探保网络科技(广州)有限公司 | Insurance recommendation method and system based on electronic commerce platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103473354A (en) | Insurance recommendation system framework and insurance recommendation method based on e-commerce platform | |
| US11507551B2 (en) | Analytics based on scalable hierarchical categorization of web content | |
| Zhang et al. | Product innovation based on online review data mining: a case study of Huawei phones | |
| Liu et al. | Analyzing changes in hotel customers’ expectations by trip mode | |
| Lu et al. | BizSeeker: a hybrid semantic recommendation system for personalized government‐to‐business e‐services | |
| Sohail et al. | Feature extraction and analysis of online reviews for the recommendation of books using opinion mining technique | |
| US7685091B2 (en) | System and method for online information analysis | |
| US20110225152A1 (en) | Constructing a search-result caption | |
| US20190220902A1 (en) | Information analysis apparatus, information analysis method, and information analysis program | |
| CN102411754A (en) | Personalized recommendation method based on commodity property entropy | |
| CN104933239A (en) | Hybrid model based personalized position information recommendation system and realization method therefor | |
| CN104834686A (en) | Video recommendation method based on hybrid semantic matrix | |
| CN105183727A (en) | Method and system for recommending book | |
| WO2020256854A1 (en) | Data sampling for model exploration | |
| Jansen et al. | Investigating customer click through behaviour with integrated sponsored and nonsponsored results | |
| CN106447463A (en) | Commodity recommendation method based on Markov decision-making process model | |
| US9317584B2 (en) | Keyword index pruning | |
| CN102968506A (en) | Personalized collaborative filtering recommendation method based on extension characteristic vectors | |
| CN104268292A (en) | Label word library update method of portrait system | |
| CN104484431A (en) | Multi-source individualized news webpage recommending method based on field body | |
| US20180139296A1 (en) | Method of producing browsing attributes of users, and non-transitory computer-readable storage medium | |
| Krestel et al. | Diversifying customer review rankings | |
| Li et al. | Optimal keywords grouping in sponsored search advertising under uncertain environments | |
| Niu et al. | Product hierarchy-based customer profiles for electronic commerce recommendation | |
| Ji et al. | Selection of best keywords: A poisson regression model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20131225 |